检索结果-内蒙古大学图书馆

Physica A: Statistical Mechanics and its Applications 2010年第13期389卷 2675-2681页

作者： Chuang Liu Wei-Xing Zhou Wei-Kang Yuan School of Business East China University of Science and Technology Shanghai 200237 China Engineering Research Center of Process Systems Engineering (Ministry of Education) East China University of Science and Technology Shanghai 200237 China Research Center for Econophysics East China University of Science and Technology Shanghai 200237 China School of Science East China University of Science and Technology Shanghai 200237 China Research Center on Fictitious Economics & Data Science Chinese Academy of Sciences Beijing 100080 China State Key Laboratory of Chemical Engineering East China University of Science and Technology Shanghai 200237 China

We study the statistical properties of complex networks constructed from time series of energy dissipation rates in three-dimensional fully developed turbulence using the visibility algorithm. The degree distribution is found to have a power-law tail with the tail exponent α = 3.0 . The exponential relation between the number of the boxes N B and the box size l B based on the edge-covering box-counting method illustrates that the network is not self-similar, which is also confirmed by the hub-hub attraction according to the visibility algorithm. In addition, it is found that the skeleton of the visibility network exhibits excellent allometric scaling with the scaling exponent η = 1.163 ± 0.005 .

关键词： Turbulence Energy dissipation rate Visibility graph Degree distribution Self-similarity Allometric scaling

A Novel Texture Generation Super Resolution Model

学校读者我要写书评

暂无评论

Procedia Computer Science 2019年 162卷 924-931页

作者： Biao Li Yong Shi Sujuan Li Bo Wang Zhiquan Qi Jiabin Liu School of Economics and Management University of Chinese Academy of Sciences Beijing 101408 China Research Center on Fictitious Economy and Data Science Chinese Academy of Sciences Beijing 100190 China Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing 100190 China College of Information Science and Technology University of Nebraska at Omaha NE 68182 USA Department of Otology the First Affiliated Hospital of Zhengzhou University No. 1 eastern Jianshe road Zhengzhou Henan 450052 China School of Information Technology and Management University of International Business and Economics Beijing 100029 China Department of Computer Science and Engineering Texas A&M University TX 77843 USA

Recently, super-resolution methods pursue visual pleasant details attract more attention in academic circle. Unlike former accurate driving models, they leverage new losses measured the difference of features extracting from a pre-trained deep learning model. Moreover, the popular GANs structure are introduced to approach better outputs. In general, these new visual feeling promoting losses are constrained by the learning ability of model and effected by the weakness of GANs. In order to address these problems, we propose a novel SR method to generating abundant details. Based on former SR methods and texture generated models, we combine new model constructure and integrated loss function to achieve our goal. The new constructure derives from the very thought that more information from the LR input leads to more accurate results. The new integrated loss try to decrease the weakness of each one by corresponding loss.. Experiments show that our model achieves higher quality generations than former methods.

关键词： Super Resolution Multi Scale Smooth Loss Visual Quality

A Review of Multimodal Explainable Artificial Intelligence: Past, Present and Future

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Sun, Shilin An, Wenbin Tian, Feng Nan, Fang Liu, Qidong Liu, Jun Shah, Nazaraf Chen, Ping School of Computer Science and Technology Xi’an Jiaotong University Xi’an710049 China Ministry of Education Key Laboratory of Intelligent Networks and Network Security Xi’an Jiaotong University Xi’an710049 China Faculty of Electronic and Information Engineering Xi’an Jiaotong University Xi’an710049 China Shaanxi Province Key Laboratory of Big Data Knowledge Engineering Xi’an Jiaotong University Xi’an710049 China Institute for Future Transport and Cities Coventry University Priory Street CoventryCV1 5FB United Kingdom Department of Engineering University of Massachusetts Boston BostonMA02125 United States

Artificial intelligence (AI) has rapidly developed through advancements in computational power and the growth of massive datasets. However, this progress has also heightened challenges in interpreting the "black-box" nature of AI models. To address these concerns, eXplainable AI (XAI) has emerged with a focus on transparency and interpretability to enhance human understanding and trust in AI decision-making processes. In the context of multimodal data fusion and complex reasoning scenarios, the proposal of Multimodal eXplainable AI (MXAI) integrates multiple modalities for prediction and explanation tasks. Meanwhile, the advent of Large Language Models (LLMs) has led to remarkable breakthroughs in natural language processing, yet their complexity has further exacerbated the issue of MXAI. To gain key insights into the development of MXAI methods and provide crucial guidance for building more transparent, fair, and trustworthy AI systems, we review the MXAI methods from a historical perspective and categorize them across four eras: traditional machine learning, deep learning, discriminative foundation models, and generative LLMs. We also review evaluation metrics and datasets used in MXAI research, concluding with a discussion of future challenges and directions. A project related to this review has been created at https://***/ShilinSun/mxai_review. Copyright © 2024, The Authors. All rights reserved.

关键词： data fusion

Implementation of improved RGBD 3D target detection model based on FPGA heterogeneous computing architecture

学校读者我要写书评

暂无评论

Implementation of improved RGBD 3D target detection model ba...

Chinese Control and Decision Conference, CCDC

作者： Yu Wang Wenbin Feng Chongchong Yu Xinyu Hu Yuqiu Zhang China Light Industry Key Laboratory of Industrial Internet and Big Data Beijing Technology and Business University Beijing China School of Artificial Intelligence Beijing Technology and Business University Beijing China State Key Laboratory of Coal Mine Safety Technology China Coal Technology&Engineering Group Shenyang Research Institute China Oil production Process Research Institute Oil Production Plant 3 of PetroChina Changqing Oilfield Company Yinchuan China

ISBN: (纸本)9781665478977

In order to solve the problems of low model accuracy, poor computing power, poor parallel ability and excessive power consumption in the deployment of RGBD based 3D target detection model at the embedded end, this paper first proposes an improved RGBD 3D target detection model based on ENet semantic segmentation model, which takes ENet as the semantic segmentation network, RGB image and depth information are fused to realize 3D target detection. Secondly, in order to apply the model at the edge, this paper constructs a lightweight network and cuts the network in the down-sampling stage of ENet model. Finally, this paper uses Xilinx ZCU104 as the hardware development kit, which takes FPGA as the auxiliary parallel operation unit and ARM as the main operation unit. It is a heterogeneous computing architecture with the ability to deal with complex operations. The architecture uses FPGA to accelerate the depth model in parallel, which improves the operation speed and reduces the power consumption. The test results of the model on ZCU104 are compared with other hardware. The results show that while ensuring the accuracy, the power consumption of the heterogeneous computing architecture used in this paper is 93% lower than that of Intel Xeon e5-2620 v4 CPU, the speed is 12 times higher, and the speed is more than 180 times higher than that of ARM Cortex-A53 commonly used at the edge.

关键词： Solid modeling Three-dimensional displays Power demand Computational modeling Semantic segmentation Process control Object detection

Research on Pre-view Method of Safety Level of Cascading Trip for Power Grid 6th

学校读者我要写书评

暂无评论

Research on Pre-view Method of Safety Level of Cascading Tri...

6th International Conference on Advanced Machine Learning Technologies and Applications, AMLTA 2021

作者： Deng, Huiqiong Li, Qinbin Zheng, Rongjin Li, Peiqiang Chang, Kuo-Chi School of Information Science and Engineering Fujian University of Technology No. 3 Xueyuan Road University Town Minhou Fuzhou Fujian350118 China Fujian Provincial University Engineering Research Center of Smart Grid Simulation Analysis and Integrated Control Fuzhou Fujian350118 China Fujian Provincial Key Laboratory of Big Data Mining and Applications Fujian University of Technology No. 3 Xueyuan Road University Town Minhou Fuzhou Fujian350118 China College of Mechanical & Electrical Engineering National Taipei University of Technology No. 1 Section 3 Zhongxiao East Road Taipei10608 Taiwan Department of Business Administration North Borneo University College Lot 47 Block-F Alamesra Permai Plaza 2 Jln Sulaman Kota Kinabalu Sabah88400 Malaysia

ISBN: (纸本)9783030697167

This article introduces a method by which the power grid's security level can be observed in advance based on the expected initial failure. Firstly, based on the general form of cascading trip, this paper gives a mathematical expression of grid tripping based on cascading trip relay protection action behavior. According to the mathematical expression, the relationship between grid tripping and grid node injection power is discussed. According to this relationship, the distance between the node injection power under the current operation state and the nearest critical state node injection power is taken as the index to measure the power grid's security for cascading trip. According to this index, combined with various power grid constraints before and after the initial fault, a mathematical model for obtaining this safety index is given. This model is an optimized mathematical model. For the model, this paper gives a solution idea based on particle swarm. Finally, a few cases are performed in the IEEE-14 node system, and the calculations of the cases proved the accuracy of the proposed model and method. © 2021, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Electric load flow

Two Novel Semantics of Top-k Queries Processing in Uncertain database

学校读者我要写书评

暂无评论

Two Novel Semantics of Top-k Queries Processing in Uncertain...

International Conference on Computer and Information Technology (CIT)

作者： Dexi Liu Changxuan Wan N. Xiong Laurence T. Yang Lei Chen School of Information Technology Jiangxi Key Laboratory of Data and Knowledge Engineering Jiangxi University of Finance and Economics Nanchang China Department of Computer Science Georgia State University Atlanta GA USA Department of Computer Science Saint Francis Xavier University Antigonish NS Canada Department of Computer Science HK University of Science and Technology Hong Kong China

Top-k query is a powerful technique in uncertain databases because of the existence of exponential possible worlds, and it is necessary to combine score and confidence of tuples to derive top k answers. Different semantics, the combination methods of score and confidence, lead to different results. U-kRanks and Global Top-k are two semantics of Top-k queries in uncertain database, which consider every alternative in x-tuple as single one and return the tuple which has the highest probability appearing at top k or a given rank. However, no matter which alternative (tuple) of an x-tuple appears in a possible world, it undoubtedly believes that this x-tuple appears in the same possible world accordingly. Thus, instead of ranking every individual tuple, we define two novel Top-k queries semantics in uncertain database, Uncertain x-kRanks queries (U-x-kRanks) and Global x-Top-k queries (G-x-Top-k), which return k entities according to the score and the confidence of alternatives in x-tuple, respectively. In order to reduce the search space, we present an efficient algorithm to process U-x-kRanks queries and G-x-Top-k queries. Comprehensive experiments on different data sets demonstrate the effectiveness of the proposed solutions.

关键词： Semantics Upper bound Heuristic algorithms Query processing Equations Artificial neural networks

Order-preserving pattern mining with forgetting mechanism

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Li, Yan Ma, Chenyu Gao, Rong Wu, Youxi Li, Jinyan Wang, Wenjian Wu, Xindong School of Economics and Management Hebei University of Technology Tianjin300400 China School of Artificial Intelligence Hebei University of Technology Tianjin300400 China School of Computer Science and Control Engineering Shenzhen University of Advanced Technology Shenzhen518055 China Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen518055 China School of Computer and Information Technology Shanxi University Taiyuan237016 China Key Laboratory of Knowledge Engineering with Big Data The Ministry of Education of China Hefei University of Technology Hefei230009 China

Order-preserving pattern (OPP) mining is a type of sequential pattern mining method in which a group of ranks of time series is used to represent an OPP. This approach can discover frequent trends in time series. Existing OPP mining algorithms consider data points at different time to be equally important;however, newer data usually have a more significant impact, while older data have a weaker impact. We therefore introduce the forgetting mechanism into OPP mining to reduce the importance of older data. This paper explores the mining of OPPs with forgetting mechanism (OPF) and proposes an algorithm called OPF-Miner that can discover frequent OPFs. OPF-Miner performs two tasks, candidate pattern generation and support calculation. In candidate pattern generation, OPF-Miner employs a maximal support priority strategy and a group pattern fusion strategy to avoid redundant pattern fusions. For support calculation, we propose an algorithm called support calculation with forgetting mechanism, which uses prefix and suffix pattern pruning strategies to avoid redundant support calculations. The experiments are conducted on nine datasets and 12 alternative algorithms. The results verify that OPF-Miner is superior to other competitive algorithms. More importantly, OPF-Miner yields good clustering performance for time series, since the forgetting mechanism is employed. Copyright © 2024, The Authors. All rights reserved.

关键词： Miners

Size-Invariance Matters: Rethinking Metrics and Losses for Imbalanced Multi-object Salient Object Detection

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Li, Feiran Xu, Qianqian Bao, Shilong Yang, Zhiyong Cong, Runmin Cao, Xiaochun Huang, Qingming Institute of Information Engineering Chinese Academy of Sciences Beijing China School of Cyber Security University of Chinese Academy of Sciences Beijing China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China Institute of Information Science Beijing Jiaotong University Beijing China School of Control Science and Engineering Shandong University Jinan China Key Laboratory of Machine Intelligence and System Control Ministry of Education Jinan China School of Cyber Science and Tech. Sun Yat-Sen University Shenzhen Campus China Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing China

This paper explores the size-invariance of evaluation metrics in Salient Object Detection (SOD), especially when multiple targets of diverse sizes co-exist in the same image. We observe that current metrics are size-sensitive, where larger objects are focused, and smaller ones tend to be ignored. We argue that the evaluation should be size-invariant because bias based on size is unjustified without additional semantic information. In pursuit of this, we propose a generic approach that evaluates each salient object separately and then combines the results, effectively alleviating the imbalance. We further develop an optimization framework tailored to this goal, achieving considerable improvements in detecting objects of different sizes. Theoretically, we provide evidence supporting the validity of our new metrics and present the generalization analysis of SOD. Extensive experiments demonstrate the effectiveness of our method. The code is available at https://***/Ferry-Li/SI-SOD. Copyright © 2024, The Authors. All rights reserved.

关键词： Object detection

Generative AI for Deep Reinforcement Learning: Framework, Analysis, and Use Cases

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Sun, Geng Xie, Wenwen Niyato, Dusit Mei, Fang Kang, Jiawen Du, Hongyang Mao, Shiwen College of Computer Science and Technology Jilin University Changchun130012 China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Changchun130012 China College of Computing and Data Science Nanyang Technological University Singapore639798 Singapore School of Automation Guangdong University of Technology Guangzhou510006 China Department of Electrical and Electronic Engineering The University of Hong Kong 999077 Hong Kong Department of Electrical and Computer Engineering Auburn University Auburn36830 United States

As a form of artificial intelligence (AI) technology based on interactive learning, deep reinforcement learning (DRL) has been widely applied across various fields and has achieved remarkable accomplishments. However, DRL faces certain limitations, including low sample efficiency and poor generalization. Therefore, we present how to leverage generative AI (GAI) to address these issues above and enhance the performance of DRL algorithms in this paper. We first introduce several classic GAI and DRL algorithms and demonstrate the applications of GAI-enhanced DRL algorithms. Then, we discuss how to use GAI to improve DRL algorithms from the data and policy perspectives. Subsequently, we introduce a framework that demonstrates an actual and novel integration of GAI with DRL, i.e., GAI-enhanced DRL. Additionally, we provide a case study of the framework on UAV-assisted integrated near-field/far-field communication to validate the performance of the proposed framework. Moreover, we present several future directions. Finally, the related code is available at: https://***/GAI-enhanced-DRL. Copyright © 2024, The Authors. All rights reserved.

关键词： Deep reinforcement learning

s-LWSR: Super lightweight super-resolution network

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Li, Biao Liu, Jiabin Wang, Bo Qi, Zhiquan Shi, Yong School of Economics and Management University of Chinese Academy of Sciences Beijing101408 China Research Center on Fictitious Economy and Data Science Chinese Academy of Sciences Beijing100190 China Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing100190 China School of Information Technology and Management University of International Business and Economics Beijing100029 China Department of Computer Science and Engineering Texas A&M University College StationTX77843 United States College of Information Science and Technology University of Nebraska OmahaNE68182 United States

Deep learning (DL) architectures for super-resolution (SR) normally contain tremendous parameters, which has been regarded as the crucial advantage for obtaining satisfying performance. However, with the widespread use of mobile phones for taking and retouching photos, this character greatly hampers the deployment of DL-SR models on the mobile devices. To address this problem, in this paper, we propose a super lightweight SR network: s-LWSR. There are mainly three contributions in our work. Firstly, in order to efficiently abstract features from the low resolution image, we build an information pool to mix multi-level information from the first half part of the pipeline. Accordingly, the information pool feeds the second half part with the combination of hierarchical features from the previous layers. Secondly, we employ a compression module to further decrease the size of parameters. Intensive analysis confirms its capacity of trade-off between model complexity and accuracy. Thirdly, by revealing the specific role of activation in deep models, we remove several activation layers in our SR model to retain more information for performance improvement. Extensive experiments show that our s-LWSR, with limited parameters and operations, can achieve similar performance to other cumbersome DL-SR methods. Copyright © 2019, The Authors. All rights reserved.

关键词： Chemical activation